English
Related papers

Related papers: PackForcing: Short Video Training Suffices for Lon…

200 papers

A unified autoregressive model is a Transformer-based framework that addresses diverse multimodal tasks (e.g., text, image, video) as a single sequence modeling problem under a shared token space. Such models rely on the KV-cache mechanism…

Computer Vision and Pattern Recognition · Computer Science 2026-01-09 Kunyang Li , Mubarak Shah , Yuzhang Shang

Recent advances in autoregressive video diffusion have enabled real-time frame streaming, yet existing solutions still suffer from temporal repetition, drift, and motion deceleration. We find that naively applying StreamingLLM-style…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Jung Yi , Wooseok Jang , Paul Hyunbin Cho , Jisu Nam , Heeji Yoon , Seungryong Kim

Long-form video generation presents a dual challenge: models must capture long-range dependencies while preventing the error accumulation inherent in autoregressive decoding. To address these challenges, we make two contributions. First,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Xiaofei Wu , Guozhen Zhang , Zhiyong Xu , Yuan Zhou , Qinglin Lu , Xuming He

Autoregressive (AR) video diffusion has recently emerged as a promising paradigm for long video generation, enabling causal synthesis beyond the limits of bidirectional models. To address training-inference mismatch, a series of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Zengqun Zhao , Yanzuo Lu , Ziquan Liu , Jifei Song , Jiankang Deng , Ioannis Patras

Self-forcing video generation extends a short-horizon video model to longer rollouts by repeatedly feeding generated content back in as context. This scaling path immediately exposes a systems bottleneck: the key-value (KV) cache grows with…

Machine Learning · Computer Science 2026-03-31 Suraj Ranganath , Vaishak Menon , Anish Patnaik

Recent advances in autoregressive video diffusion have enabled sequential and streaming video generation. However, long-horizon generation requires increasingly large KV caches, making efficient compression without sacrificing quality…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Peiliang Cai , Evelyn Zhang , Jiacheng Liu , Hao Lin , Ruiqi Zhang , Weile Mo , Yue Ma , Shikang Zheng , Jiehang Huang , Dongrui Liu , Linfeng Zhang

Recent approaches to real-time long video generation typically employ streaming tuning strategies, attempting to train a long-context student using a short-context (memoryless) teacher. In these frameworks, the student performs long…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Shuo Chen , Cong Wei , Sun Sun , Ping Nie , Kai Zhou , Ge Zhang , Ming-Hsuan Yang , Wenhu Chen

Autoregressive video diffusion models enable open-ended generation through local attention and KV caching. However, existing training-free long-video optimization methods mainly focus on stable extension under a single prompt, making them…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Mingqiang Wu , Weilun Feng , Zhefeng Zhang , Haotong Qin , Yuqi Li , Guoxin Fan , Xiaokun Liu , Zhulin An , Libo Huang , Yongjun Xu , Chuanguang Yang

Autoregressive (AR) video generation has emerged as a promising paradigm for long-horizon video synthesis, where each frame is generated conditioned on previously generated tokens. To accelerate inference, the KV cache is used to avoid…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Jiayi Luo , Qiyan Liu , Tengyang Wang , JunHao Liu , Jiayu Chen , Cong Wang , Hanxin Zhu , Chen Gao , Xiaobin Hu , Qingyun Sun , Zhibo Chen

Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover that attention heads in AR video diffusion transformers serve functionally distinct roles…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Jiahao Tian , Yiwei Wang , Gang Yu , Chi Zhang

We introduce Self Forcing, a novel training paradigm for autoregressive video diffusion models. It addresses the longstanding issue of exposure bias, where models trained on ground-truth context must generate sequences conditioned on their…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Xun Huang , Zhengqi Li , Guande He , Mingyuan Zhou , Eli Shechtman

Generating consistent long videos is a complex challenge: while diffusion-based generative models generate visually impressive short clips, extending them to longer durations often leads to memory bottlenecks and long-term inconsistency. In…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Wenqi Ouyang , Zeqi Xiao , Danni Yang , Yifan Zhou , Shuai Yang , Lei Yang , Jianlou Si , Xingang Pan

Autoregressive (AR) video diffusion models adopt a streaming generation framework, enabling long-horizon video generation with real-time responsiveness, as exemplified by the Self Forcing training paradigm. However, existing AR video…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Yicheng Ji , Zhizhou Zhong , Jun Zhang , Qin Yang , XiTai Jin , Ying Qin , Wenhan Luo , Shuiyang Mao , Wei Liu , Huan Li

Large Vision-Language Models (VLMs) have been extended to understand both images and videos. Visual token compression is leveraged to reduce the considerable token length of visual inputs. To meet the needs of different tasks, existing…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Chenyu Yang , Xuan Dong , Xizhou Zhu , Weijie Su , Jiahao Wang , Hao Tian , Zhe Chen , Wenhai Wang , Lewei Lu , Jifeng Dai

Diffusion models have revolutionized image and video generation, achieving unprecedented visual quality. However, their reliance on transformer architectures incurs prohibitively high computational costs, particularly when extending…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Justin Cui , Jie Wu , Ming Li , Tao Yang , Xiaojie Li , Rui Wang , Andrew Bai , Yuanhao Ban , Cho-Jui Hsieh

Scaling language models to long contexts is often bottlenecked by the size of the key-value (KV) cache. In deployed settings, long contexts are typically managed through compaction in token space via summarization. However, summarization…

Machine Learning · Computer Science 2026-05-28 Adam Zweiger , Xinghong Fu , Han Guo , Yoon Kim

Autoregressive video generation enables streaming and open-ended long video synthesis, but still suffers from long-term degradation caused by accumulated errors. Existing KVCache strategies usually apply unified historical-frame retention,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Jiayu Chen , Junbei Tang , Wenbiao Zhao , Maoliang Li , Jiayi Luo , Zihao Zheng , Jiawei Yang , Guojie Luo , Xiang Chen

Transformer-based large language models (LLMs) have demonstrated remarkable potential across a wide range of practical applications. However, long-context inference remains a significant challenge due to the substantial memory requirements…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-09 Bo Jiang , Taolue Yang , Youyuan Liu , Xubin He , Sheng Di , Sian Jin

Video tokenizers are essential for latent video diffusion models, converting raw video data into spatiotemporally compressed latent spaces for efficient training. However, extending state-of-the-art video tokenizers to achieve a temporal…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Aniruddha Mahapatra , Long Mai , David Bourgin , Yitian Zhang , Feng Liu

Unlike offline processing, streaming video vision-language models face two fundamental constraints: causality and accumulation. Causality prevents access to future frames that offline methods exploit, while accumulation causes tokens to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Xueyi Chen , Keda Tao , Kele Shao , Huan Wang
‹ Prev 1 2 3 10 Next ›